Update app.py

app.py

@@ -1,64 +1,45 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+import torch
+from sentence_transformers import SentenceTransformer
+from torch.nn.functional import cosine_similarity
+
+# モデルの読み込み
+model = SentenceTransformer("Shuu12121/CodeCloneDetection-ModernBERT-Owl")
+model.eval()
+
+# 閾値設定（安定性の高い0.9推奨）
+THRESHOLD = 0.9
+
+
+def detect_clone(code1, code2):
+    if not code1.strip() or not code2.strip():
+        return "❌ どちらのコードも入力してください", ""
+
+    with torch.no_grad():
+        embeddings = model.encode([code1, code2], convert_to_tensor=True)
+        sim_score = cosine_similarity(embeddings[0].unsqueeze(0), embeddings[1].unsqueeze(0)).item()
+
+    result = (
+        f"🟢 類似度: {sim_score:.4f}\n→ これらのコードは **クローン** と判定されます。"
+        if sim_score >= THRESHOLD
+        else f"🔴 類似度: {sim_score:.4f}\n→ これらのコードは **クローンではありません**。"
+    )
+    return result, sim_score
+
+# Gradioインターフェースの作成
+demo = gr.Interface(
+    fn=detect_clone,
+    inputs=[
+        gr.Textbox(label="コードスニペット1", lines=10, placeholder="例: def add(a, b): return a + b"),
+        gr.Textbox(label="コードスニペット2", lines=10, placeholder="例: def sum(x, y): return x + y"),
+    ],
+    outputs=[
+        gr.Markdown(label="判定結果"),
+        gr.Number(label="Cosine Similarity")
     ],
+    title="Code Clone Detection with ModernBERT-Owl 🦉",
+    description="Shuu12121/CodeModernBERT-Owl によって構築された Sentence-BERT モデルを使用し、コードクローンを検出します。"
 )
 
-
 if __name__ == "__main__":
     demo.launch()